{"id":"W2564529810","doi":"10.1109/crv.2016.14","title":"Computer Vision-Based Detection of Violent Individual Actions Witnessed by Crowds","year":2016,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Crowds; Computer science; Upload; Reliability (semiconductor); Artificial intelligence; Computer vision; Exploit; Crowd psychology; Action (physics); Crowd simulation; Human–computer interaction; Motion (physics); Amateur; Computer security; Machine learning; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001281683,0.00009971059,0.0001053395,0.0001192667,0.0001298099,0.0000443608,0.000413776,0.00007105969,0.00005731883],"category_scores_gemma":[0.000004978056,0.00006825017,0.0000735159,0.0003551026,0.00006617841,0.0002638909,0.00009059102,0.00005274275,0.00003012341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003597759,"about_ca_system_score_gemma":0.00003480803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003262548,"about_ca_topic_score_gemma":0.000006549452,"domain_scores_codex":[0.9991179,0.0000311799,0.0002306819,0.0002793975,0.0002007602,0.0001401074],"domain_scores_gemma":[0.9991821,0.00009268039,0.0001160233,0.0004380182,0.000104551,0.00006662586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000007381882,0.0002163161,0.000129079,0.000006074687,0.00001606299,2.957236e-7,0.00001766403,0.00002600753,0.4465585,0.01027057,0.004002707,0.5387493],"study_design_scores_gemma":[0.0003572156,0.000349224,0.002837824,0.00002432624,0.000007057544,0.000004452226,0.00000387181,0.01760661,0.9616869,0.001118369,0.01583678,0.0001673468],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02127397,0.000006950152,0.9766442,0.001083907,0.00009904963,0.0001588553,0.00001109077,0.000407033,0.0003150016],"genre_scores_gemma":[0.9638782,0.00000525723,0.03561565,0.0002003056,0.00002995291,0.00006334917,0.000001715265,0.000006674851,0.0001988626],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9426042,"threshold_uncertainty_score":0.2783161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01264650958754628,"score_gpt":0.2577765590610312,"score_spread":0.2451300494734849,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}